Time-Series Image-Based Automated Monitoring Framework for Temporary Facilities : Focusing on Installation and Retention Period

다국어 초록 (Multilingual Abstract)

In the construction industry, ensuring the proper installation, retention, and dismantling of temporary structures, such as jack supports, is critical to maintaining safety and project timelines. However, inconsistencies between on-site data and construction documentation remain a significant challenge. To address this, this study proposes an integrated monitoring framework that combines computer vision-based object detection and document recognition techniques. The system utilizes YOLOv5 for detecting jack supports in both construction drawings and on-site images captured through wearable cameras, while Optical Character Recognition (OCR) and Natural Language Processing (NLP) extract installation and dismantling timelines from work orders. The proposed framework enables continuous monitoring and ensures compliance with retention periods by aligning on-site data with documented requirements. The analysis includes 23 jack supports monitored daily over 28 days under varying environmental conditions, including lighting changes and structural configurations. The results demonstrate that the system achieves an average detection accuracy of 94.1%, effectively identifying discrepancies and reducing misclassifications caused by structural similarities and environmental variations. To further enhance detection reliability, methods such as color differentiation, construction plan overlays, and vertical segmentation were implemented, significantly improving performance. This study validates the effectiveness of integrating visual and textual data sources in dynamic construction environments. The study supports the development of automated monitoring systems by improving accuracy and safety measures while reducing manual intervention, offering practical insights for future construction site management.

목차 (Table of Contents)

• Ⅰ. Introduction 1
• 1.1 Introduction 1
• 1.2 Research background and literature review 3
• 1.2.1 Advances in Construction Document Monitoring 4
• 1.2.2 Monitoring Challenges and Vision-Based Solutions 5
• 1.2.3 Integration of Monitoring Systems 6
• Ⅱ. Methodology 7
• 2.1 Research Framework 7
• 2.2 Data Collection and Preprocessing 10
• 2.3 Object Detection Algorithm 12
• 2.4 Recognition of Document Information 12
• 2.5 Matching Process between Drawings and On-Site Detection 16
• 2.6 Verification of Jack Support Installation 17
• 2.7 Verification of Jack Support Retention Compliance 18
• Ⅲ. Results 19
• 3.1 Object Detection Results 19
• 3.1.1 Jack Support Detection on Drawing 19
• 3.1.2 On-Site Jack Support Detection 22
• 3.2 Document Recognition Results 24
• 3.3 Jack Support Installation Determination 26
• 3.4 Determining Retention Compliance 27
• 3.4.1 Accuracy Evaluation of Jack Support Retention Period Compliance Detection 30
• Ⅳ. Discussion 32
• 4.1 Contribution and Limitations 32
• 4.2 Solution for Preventing the Misdetection of Ceiling Pipes as Jack Supports 42
• 4.2.1 Using a Consistent Color Pattern for Ceiling Pipes 33
• 4.2.2 Applying Construction Drawings for Ceiling Pipes 34
• 4.2.3 Jack Support Detection through Vertical Segmentation 35
• 4.2.4 Comparison of Three Methods to Prevent Misdetection of Ceiling Pipes as Jack Support 36
• 4.3 Additional Solutions for False Detection 38
• 4.3.1 Multi-Angle Image Analysis 38
• 4.3.2 Automated Multi-Angle Image Analysis Using UGV 39
• Ⅴ. Conclusions 40
• 5.1 Contribution 40
• References 42
• 국문초록 63